TY - JOUR
T1 - Using Machine-Learning for Prediction of the Response to Cardiac Resynchronization Therapy
T2 - The SMART-AV Study
AU - Howell, Stacey J.
AU - Stivland, Tim
AU - Stein, Kenneth
AU - Ellenbogen, Kenneth A.
AU - Tereshchenko, Larisa G.
N1 - Funding Information:
This work was supported in part by the National Institutes of Health (HL118277), the Medical Research Foundation of Oregon, and Oregon Health and Science University President Bridge funding (to Dr Tereshchenko). The SMART-AV trial was sponsored by Boston Scientific. Drs Stivland and Stein are employees of Boston Scientific. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose.
Publisher Copyright:
© 2021 American College of Cardiology Foundation
PY - 2021/12
Y1 - 2021/12
N2 - Objectives: This study aimed to apply machine learning (ML) to develop a prediction model for short-term cardiac resynchronization therapy (CRT) response to identifying CRT candidates for early multidisciplinary CRT heart failure (HF) care. Background: Multidisciplinary optimization of cardiac resynchronization therapy (CRT) delivery can improve long-term CRT outcomes but requires substantial staff resources. Methods: Participants from the SMART-AV (SmartDelay-Determined AV Optimization: Comparison of AV Optimization Methods Used in Cardiac Resynchronization Therapy [CRT]) trial (n = 741; age: 66 ± 11 years; 33% female; 100% New York Heart Association HF functional class III-IV; 100% ejection fraction ≤35%) were randomly split into training/testing (80%; n = 593) and validation (20%; n = 148) samples. Baseline clinical, electrocardiographic, echocardiographic, and biomarker characteristics, and left ventricular (LV) lead position (43 variables) were included in 8 ML models (random forests, convolutional neural network, lasso, adaptive lasso, plugin lasso, elastic net, ridge, and logistic regression). A composite of freedom from death and HF hospitalization and a >15% reduction in LV end-systolic volume index at 6 months after CRT was the end point. Results: The primary end point was met by 337 patients (45.5%). The adaptive lasso model was the most more accurate (area under the receiver operating characteristic curve: 0.759; 95% CI: 0.678-0.840), well calibrated, and parsimonious (19 predictors; nearly half potentially modifiable). Participants in the 5th quintile compared with those in the 1st quintile of the prediction model had 14-fold higher odds of composite CRT response (odds ratio: 14.0; 95% CI: 8.0-14.4). The model predicted CRT response with 70% accuracy, 70% sensitivity, and 70% specificity, and should be further validated in prospective studies. Conclusions: ML predicts short-term CRT response and thus may help with CRT procedure and early post-CRT care planning.
AB - Objectives: This study aimed to apply machine learning (ML) to develop a prediction model for short-term cardiac resynchronization therapy (CRT) response to identifying CRT candidates for early multidisciplinary CRT heart failure (HF) care. Background: Multidisciplinary optimization of cardiac resynchronization therapy (CRT) delivery can improve long-term CRT outcomes but requires substantial staff resources. Methods: Participants from the SMART-AV (SmartDelay-Determined AV Optimization: Comparison of AV Optimization Methods Used in Cardiac Resynchronization Therapy [CRT]) trial (n = 741; age: 66 ± 11 years; 33% female; 100% New York Heart Association HF functional class III-IV; 100% ejection fraction ≤35%) were randomly split into training/testing (80%; n = 593) and validation (20%; n = 148) samples. Baseline clinical, electrocardiographic, echocardiographic, and biomarker characteristics, and left ventricular (LV) lead position (43 variables) were included in 8 ML models (random forests, convolutional neural network, lasso, adaptive lasso, plugin lasso, elastic net, ridge, and logistic regression). A composite of freedom from death and HF hospitalization and a >15% reduction in LV end-systolic volume index at 6 months after CRT was the end point. Results: The primary end point was met by 337 patients (45.5%). The adaptive lasso model was the most more accurate (area under the receiver operating characteristic curve: 0.759; 95% CI: 0.678-0.840), well calibrated, and parsimonious (19 predictors; nearly half potentially modifiable). Participants in the 5th quintile compared with those in the 1st quintile of the prediction model had 14-fold higher odds of composite CRT response (odds ratio: 14.0; 95% CI: 8.0-14.4). The model predicted CRT response with 70% accuracy, 70% sensitivity, and 70% specificity, and should be further validated in prospective studies. Conclusions: ML predicts short-term CRT response and thus may help with CRT procedure and early post-CRT care planning.
KW - cardiac resynchronization therapy
KW - machine learning
UR - http://www.scopus.com/inward/record.url?scp=85120991403&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85120991403&partnerID=8YFLogxK
U2 - 10.1016/j.jacep.2021.06.009
DO - 10.1016/j.jacep.2021.06.009
M3 - Article
C2 - 34454883
AN - SCOPUS:85120991403
SN - 2405-5018
VL - 7
SP - 1505
EP - 1515
JO - JACC: Clinical Electrophysiology
JF - JACC: Clinical Electrophysiology
IS - 12
ER -